On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “Diplomacy”

Learning to Play No-Press Diplomacy with Best Response Policy Iterationcs.LG

Deep RL improves Diplomacy performance, outperforming previous methods.

problem Applying RL to complex, many-agent, simultaneous-move games like Diplomacy.

method Best response policy iteration and fictitious play approximation.

result Deep RL agents convincingly outperform previous Diplomacy agents.

Deep RL Policy iteration Fictitious play Diplomacy Best response

2020-06-08abs ↗pdf ↗

Evolving efficiency and robustness of global oil trade networksq-fin.ST

This study analyzes global oil trade networks to assess their efficiency and robustness.

problem Dynamic monitoring and warning of international trade risks in global oil trade.

method Constructing unweighted and weighted global oil trade networks (OTNs) using UN Comtrade data from 1988 to 2017, and applying complex network theories.

result Efficiency of oil flows increases with complexity of OTNs, and weighted efficiency indicators highlight major events.

global oil trade network analysis efficiency robustness critical economies

2020-04-11abs ↗pdf ↗